utf8 decode python code example

Example 1: python unicode point to utf8 string

#! /usr/bin/python3
import re

def makeNice(s):
    return re.subn('(#U[0-9a-f]{4})', lambda cp: chr(int(cp.groups()[0][2:],16)), s) [0]

a = '-#U2605-#U79c1-'
print(a, makeNice(a))

Example 2: decode utf8 whit python

import codecs
BLOCKSIZE = 1048576 # or some other, desired size in bytes
with codecs.open(sourceFileName, "r", "your-source-encoding") as sourceFile:
    with codecs.open(targetFileName, "w", "utf-8") as targetFile:
        while True:
            contents = sourceFile.read(BLOCKSIZE)
            if not contents:
                break
            targetFile.write(contents)